Prediction

ID

llfudnitjraaldwtgumsxp6h3m

Status

Succeeded

Source

Web

Hardware

–

Total duration

–

Created

over 3 years ago by @chenxwh

Input

jpeg: "40"
image
noise: "15"
task_type: Real-World Image Super-Resolution

{
  "jpeg": "40",
  "image": "https://replicate.delivery/mgxm/247abcb1-a333-4a4a-8abf-5f51363e95e0/0014.jpg",
  "noise": "15",
  "task_type": "Real-World Image Super-Resolution"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
  {
    input: {
      jpeg: "40",
      image: "https://replicate.delivery/mgxm/247abcb1-a333-4a4a-8abf-5f51363e95e0/0014.jpg",
      noise: "15",
      task_type: "Real-World Image Super-Resolution"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    input={
        "jpeg": "40",
        "image": "https://replicate.delivery/mgxm/247abcb1-a333-4a4a-8abf-5f51363e95e0/0014.jpg",
        "noise": "15",
        "task_type": "Real-World Image Super-Resolution"
    }
)

# The jingyunliang/swinir model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/jingyunliang/swinir/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    "input": {
      "jpeg": "40",
      "image": "https://replicate.delivery/mgxm/247abcb1-a333-4a4a-8abf-5f51363e95e0/0014.jpg",
      "noise": "15",
      "task_type": "Real-World Image Super-Resolution"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Loading...

jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a

Prediction

Model

ID

ehtvj4ext5fazcurdrw34jictq

Status

Succeeded

Source

Web

Hardware

–

Total duration

–

Created

over 3 years ago by @chenxwh

Input

jpeg: "40"
image
noise: "15"
task_type: Grayscale Image Denoising

{
  "jpeg": "40",
  "image": "https://replicate.delivery/mgxm/a58739dd-78d0-4095-95f7-40122421abfe/10.png",
  "noise": "15",
  "task_type": "Grayscale Image Denoising"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
  {
    input: {
      jpeg: "40",
      image: "https://replicate.delivery/mgxm/a58739dd-78d0-4095-95f7-40122421abfe/10.png",
      noise: "15",
      task_type: "Grayscale Image Denoising"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    input={
        "jpeg": "40",
        "image": "https://replicate.delivery/mgxm/a58739dd-78d0-4095-95f7-40122421abfe/10.png",
        "noise": "15",
        "task_type": "Grayscale Image Denoising"
    }
)

# The jingyunliang/swinir model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/jingyunliang/swinir/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    "input": {
      "jpeg": "40",
      "image": "https://replicate.delivery/mgxm/a58739dd-78d0-4095-95f7-40122421abfe/10.png",
      "noise": "15",
      "task_type": "Grayscale Image Denoising"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Loading...

jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a

Prediction

Model

ID

3gd2cdkyjjdwdgkihg72cx6ib4

Status

Succeeded

Source

Web

Hardware

–

Total duration

–

Created

over 3 years ago by @chenxwh

Input

jpeg: "40"
image
noise: "15"
task_type: JPEG Compression Artifact Reduction

{
  "jpeg": "40",
  "image": "https://replicate.delivery/mgxm/b0a3f6c2-225a-49da-b14e-12196ab43af3/lena.bmp",
  "noise": "15",
  "task_type": "JPEG Compression Artifact Reduction"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
  {
    input: {
      jpeg: "40",
      image: "https://replicate.delivery/mgxm/b0a3f6c2-225a-49da-b14e-12196ab43af3/lena.bmp",
      noise: "15",
      task_type: "JPEG Compression Artifact Reduction"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    input={
        "jpeg": "40",
        "image": "https://replicate.delivery/mgxm/b0a3f6c2-225a-49da-b14e-12196ab43af3/lena.bmp",
        "noise": "15",
        "task_type": "JPEG Compression Artifact Reduction"
    }
)

# The jingyunliang/swinir model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/jingyunliang/swinir/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    "input": {
      "jpeg": "40",
      "image": "https://replicate.delivery/mgxm/b0a3f6c2-225a-49da-b14e-12196ab43af3/lena.bmp",
      "noise": "15",
      "task_type": "JPEG Compression Artifact Reduction"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Loading...

jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a

Prediction

Model

ID

ge322t2ffngrjjjjucgsbg474u

Status

Succeeded

Source

Web

Hardware

–

Total duration

–

Created

over 3 years ago

Input

jpeg: "40"
image
noise: "15"
task_type: Grayscale Image Denoising

{
  "jpeg": "40",
  "image": "https://replicate.delivery/mgxm/31584856-9020-4c99-9a24-babcd7173998/05.png",
  "noise": "15",
  "task_type": "Grayscale Image Denoising"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
  {
    input: {
      jpeg: "40",
      image: "https://replicate.delivery/mgxm/31584856-9020-4c99-9a24-babcd7173998/05.png",
      noise: "15",
      task_type: "Grayscale Image Denoising"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    input={
        "jpeg": "40",
        "image": "https://replicate.delivery/mgxm/31584856-9020-4c99-9a24-babcd7173998/05.png",
        "noise": "15",
        "task_type": "Grayscale Image Denoising"
    }
)

# The jingyunliang/swinir model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/jingyunliang/swinir/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    "input": {
      "jpeg": "40",
      "image": "https://replicate.delivery/mgxm/31584856-9020-4c99-9a24-babcd7173998/05.png",
      "noise": "15",
      "task_type": "Grayscale Image Denoising"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Loading...

jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a

Prediction

Model

ID

csp4aecvzneq7pmzoyzyuwu4ci

Status

Succeeded

Source

Web

Hardware

–

Total duration

–

Created

over 3 years ago by @chenxwh

Input

jpeg: "40"
image
noise: "15"
task_type: Real-World Image Super-Resolution-Large

{
  "jpeg": "40",
  "image": "https://replicate.delivery/mgxm/efd1b6b0-4d79-4a42-ab31-2dcd29754a2d/chip.png",
  "noise": "15",
  "task_type": "Real-World Image Super-Resolution-Large"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
  {
    input: {
      jpeg: "40",
      image: "https://replicate.delivery/mgxm/efd1b6b0-4d79-4a42-ab31-2dcd29754a2d/chip.png",
      noise: "15",
      task_type: "Real-World Image Super-Resolution-Large"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jingyunliang/swinir:a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    input={
        "jpeg": "40",
        "image": "https://replicate.delivery/mgxm/efd1b6b0-4d79-4a42-ab31-2dcd29754a2d/chip.png",
        "noise": "15",
        "task_type": "Real-World Image Super-Resolution-Large"
    }
)

# The jingyunliang/swinir model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/jingyunliang/swinir/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run jingyunliang/swinir using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "a6655af5d286c0362310303ace66a638b0e1e01be584a327f18d0d6c8c00025a",
    "input": {
      "jpeg": "40",
      "image": "https://replicate.delivery/mgxm/efd1b6b0-4d79-4a42-ab31-2dcd29754a2d/chip.png",
      "noise": "15",
      "task_type": "Real-World Image Super-Resolution-Large"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Loading...